robdasi

brief-builder

Set up a site's voice and its anti-repetition memory once, so every later article sounds human and never recycles a story, a source, or an opening. Captures the business, builds a voice profile (defaults plus a client-voice override and a lexicon), and starts two banks: the E-E-A-T stories used and the stat sources used. Run first, once per site. The other content-pipeline skills load its output. Produces a site brief, a voice profile, and the banks, then stops.

Data & Documents Listed

competitor-analyzer

Read at least three competitors' actual content before a word gets written, and turn it into a gap analysis and a word count to beat. Pulls the live SERP, reads the real pages (not just their headings), and reports what they all cover, what to go deeper on, what nobody covers, and the target length. Pulls real People Also Ask from the SERP, never invented. Run after keyword-researcher, before outline-drafter. Produces a gap analysis and stops.

draft-writer

Write the article to the outline, in the site's real voice, with every number sourced and nothing recycled. Holds the voice defaults and the anti-detection blocklist, front-loads the citable answer, weaves links into real sentences, uses the one unique E-E-A-T story, and never invents a statistic. Run after outline-drafter. This is the method, not a magic writer. Produces a draft and stops.

Data & Documents Listed

keyword-researcher

Turn a topic into a keyword decision, title-first. Picks the main keyword that already sits in the title so the title never gets rewritten, ranks candidates by a strict priority (title match over volume, always), and builds a deliberate spread of secondary keywords by intent, returning none rather than forcing irrelevant ones. Run after brief-builder, before competitor-analyzer. Produces a keyword brief and stops.

outline-drafter

Turn the gap analysis into an outline that fills the gap, answers real questions, and is built to be cited. Sets the sections from table-stakes plus the unique angle, turns PAA into question-form H2s, places the 40-60 word answer capsule and the cited stats up top, plans the one unique E-E-A-T story, and forces an opening that doesn't match the site's other articles. Run after competitor-analyzer, before draft-writer. Produces an outline and stops.

publish-prep

Run the finished draft through the full pre-publish check before it goes live. Verifies the SEO basics, the image and link rules, the humanisation and anti-repetition rules, the E-E-A-T and differentiation rules, and fact-checks every number against its named source. Builds the meta, slug, key takeaways, and FAQ-from-real-PAA. Run last in the content pipeline. Produces a publish package and a pass/fail checklist, then stops.

build-spec

Write the spec before you let an AI build an automation. Turns a one-line "build me a thing that..." into a reviewable build spec: the job, the trigger, inputs and outputs, the happy path, state and idempotency, failure modes, rate limits, observability, a cost ceiling, and acceptance criteria. Use this BEFORE asking Claude (or any agent) to build a workflow, integration, or scheduled job, so it builds the thing that survives week two instead of the thing that demos. It stops at the spec. Building to the spec is the next step.

content-preflight

Run the 12-point pre-write checklist before writing any SEO article or page. Turns a target keyword into a research-backed content brief: search intent, content gaps, real People Also Ask, semantic terms, entities to cite, internal links, the EEAT angle, and an outline. Use this BEFORE writing any piece of SEO content so the page is built on what actually ranks, not a guess. It stops at the brief. Writing to the brief is the next step (yours, or your writer's).

eval-set

Decide whether an automation, agent, or skill actually works, without pretending you run a test suite. Turns the output's contract into a schema, a pre-ship checklist of must-be-true invariants, and a completeness judge with a numeric gate, plus one regression case per bug already found. Use this before you trust a build, before a model upgrade silently breaks it, or before each unattended run. Produces a checks file and stops.

outreach-research-pass

Do the research before a single cold line is written. Gates on ICP first, sources prospects by the intent signal itself (not generic lists scored after the fact), stacks and dates every signal onto one identity, then runs a strict two-pass: score and classify and emit a single angle, then personalise from that angle. Spend is gated on the score; every claim must trace to a verified signal. Use this before personalising any outreach at scale. Produces a per-prospect dossier and stops.

pipeline-replay

Make a multi-step agent or automation pipeline safely re-runnable. Maps each step to its side-effect class (read / internal-write / external-write / irreversible), assigns idempotency keys, finds the safe resume point after a failure, and builds a dedup table so a retry never double-sends, double-charges, or double-posts. Use this when designing a Trigger.dev / cron / multi-step pipeline, or after one ran twice and did the damage twice. Produces a replay plan and stops.

scraper-contract

Spec a scraper that fails loudly instead of returning quiet garbage. Defines a closed failure taxonomy (unreachable / blocked / timeout / rate-limited / invalid / empty / unknown), makes empty output a hard failure not a success, sets a per-field stability tier and the minimum identifier a record must have to be accepted, and decides what counts as a broken run. Use this before pointing Claude, Apify, or Playwright at a site. Produces a scrape contract and stops.